mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-27 07:39:05 +01:00
6ab45dd3ec
* Add cpu_used (all-cpu_idle) to CpustatCollector * Update to line-protocol/v2 * Update runonce.yml with Golang 1.20 * Update fsnotify in LIKWID Collector * Use not a pointer to line-protocol.Encoder * Simplify Makefile * Use only as many arguments as required * Allow sum function to handle non float types * Allow values to be a slice of type float64, float32, int, int64, int32, bool * Use generic function to simplify code * Add missing case for type []int32 * Use generic function to compute minimum * Use generic function to compute maximum * Use generic function to compute average * Add error value to sumAnyType * Use generic function to compute median * For older versions of go slices is not part of the installation * Remove old entries from go.sum * Use simpler sort function * Compute metrics ib_total and ib_total_pkts * Add aggregated metrics. Add missing units * Update likwidMetric.go Fixes a potential bug when `fsnotify.NewWatcher()` fails with an error * Completly avoid memory allocations in infinibandMetric read() * Fixed initialization: Initalization and measurements should run in the same thread * Add safe.directory to Release action * Fix path after installation to /usr/bin after installation * ioutil.ReadFile is deprecated: As of Go 1.16, this function simply calls os.ReadFile * Switch to package slices from the golang 1.21 default library * Read file line by line * Read file line by line * Read file line by line * Use CamelCase * Use CamelCase * Fix function getNumaDomain, it always returned 0 * Avoid type conversion by using Atoi Avoid copying structs by using pointer access Increase readability with CamelCase variable names * Add caching * Cache CpuData * Cleanup * Use init function to initalize cache structure to avoid multi threading problems * Reuse information from /proc/cpuinfo * Avoid slice cloning. Directly use the cache * Add DieList * Add NumaDomainList and SMTList * Cleanup * Add comment * Lookup core ID from /sys/devices/system/cpu, /proc/cpuinfo is not portable * Lookup all information from /sys/devices/system/cpu, /proc/cpuinfo is not portable * Correctly handle lists from /sys * Add Simultaneous Multithreading siblings * Replace deprecated thread_siblings_list by core_cpus_list * Reduce number of required slices * Allow to send total values per core, socket and node * Send all metrics with same time stamp calcEventsetMetrics does only computiation, counter measurement is done before * Input parameters should be float64 when evaluating to float64 * Send all metrics with same time stamp calcGlobalMetrics does only computiation, counter measurement is done before * Remove unused variable gmresults * Add comments * Updated go packages * Add build with golang 1.21 * Switch to checkout action version 4 * Switch to setup-go action version 4 * Add workflow_dispatch to allow manual run of workflow * Add workflow_dispatch to allow manual run of workflow * Add release build jobs to runonce.yml * Switch to golang 1.20 for RHEL based distributions * Use dnf to download golang * Remove golang versions before 1.20 * Upgrade Ubuntu focal -> jammy * Pipe golang tar package directly to tar * Update golang version * Fix Ubuntu version number * Add links to ipmi and redfish receivers * Fix http server addr format * github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol * Corrected spelling * Add some comments * github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol * Allow other fields not only field "value" * Add some basic debugging documentation * Add some basic debugging documentation * Use a lock for the flush timer * Add tags in lexical order as required by AddTag() * Only access meta data, when it gets used as tag * Use slice to store lexialicly orderd key value pairs * Increase golang version requirement to 1.20. * Avoid package cmp to allow builds with golang v1.20 * Fix: Error NVML library not found did crash cc-metric-collector with "SIGSEGV: segmentation violation" * Add config option idle_timeout * Add basic authentication support * Add basic authentication support * Avoid unneccessary memory allocations * Add documentation for send_*_total values * Use generic package maps to clone maps * Reuse flush timer * Add Influx client options * Reuse ccTopology functionality * Do not store unused topology information * Add batch_size config * Cleanup * Use stype and stype-id for the NIC in NetstatCollector * Wait for concurrent flush operations to finish * Be more verbose in error messages * Reverted previous changes. Made the code to complex without much advantages * Use line protocol encoder * Go pkg update * Stop flush timer, when immediatelly flushing * Fix: Corrected unlock access to batch slice * Add config option to specify whether to use GZip compression in influx write requests * Add asynchron send of encoder metrics * Use DefaultServeMux instead of github.com/gorilla/mux * Add config option for HTTP keep-alives * Be more strict, when parsing json * Add config option for HTTP request timeout and Retry interval * Allow more then one background send operation * Fix %sysusers_create_package args (#108) %sysusers_create_package requires two arguments. See: https://github.com/systemd/systemd/blob/main/src/rpm/macros.systemd.in#L165 * Add nfsiostat to list of collectors --------- Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <holgerob@gmx.de> Co-authored-by: Obihörnchen <obihoernchende@gmail.com>
170 lines
3.8 KiB
Go
170 lines
3.8 KiB
Go
package collectors
|
|
|
|
import (
|
|
"bufio"
|
|
"encoding/json"
|
|
|
|
"fmt"
|
|
"os"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
|
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
|
|
)
|
|
|
|
// CPUFreqCollector
|
|
// a metric collector to measure the current frequency of the CPUs
|
|
// as obtained from /proc/cpuinfo
|
|
// Only measure on the first hyperthread
|
|
type CPUFreqCpuInfoCollectorTopology struct {
|
|
isHT bool
|
|
tagSet map[string]string
|
|
}
|
|
|
|
type CPUFreqCpuInfoCollector struct {
|
|
metricCollector
|
|
topology []CPUFreqCpuInfoCollectorTopology
|
|
}
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
|
|
// Check if already initialized
|
|
if m.init {
|
|
return nil
|
|
}
|
|
|
|
m.setup()
|
|
|
|
m.name = "CPUFreqCpuInfoCollector"
|
|
m.parallel = true
|
|
m.meta = map[string]string{
|
|
"source": m.name,
|
|
"group": "CPU",
|
|
"unit": "MHz",
|
|
}
|
|
|
|
const cpuInfoFile = "/proc/cpuinfo"
|
|
file, err := os.Open(cpuInfoFile)
|
|
if err != nil {
|
|
return fmt.Errorf("failed to open file '%s': %v", cpuInfoFile, err)
|
|
}
|
|
defer file.Close()
|
|
|
|
// Collect topology information from file cpuinfo
|
|
foundFreq := false
|
|
processor := ""
|
|
coreID := ""
|
|
physicalPackageID := ""
|
|
m.topology = make([]CPUFreqCpuInfoCollectorTopology, 0)
|
|
coreSeenBefore := make(map[string]bool)
|
|
|
|
// Read cpuinfo file, line by line
|
|
scanner := bufio.NewScanner(file)
|
|
for scanner.Scan() {
|
|
lineSplit := strings.Split(scanner.Text(), ":")
|
|
if len(lineSplit) == 2 {
|
|
key := strings.TrimSpace(lineSplit[0])
|
|
value := strings.TrimSpace(lineSplit[1])
|
|
switch key {
|
|
case "cpu MHz":
|
|
// frequency
|
|
foundFreq = true
|
|
case "processor":
|
|
processor = value
|
|
case "core id":
|
|
coreID = value
|
|
case "physical id":
|
|
physicalPackageID = value
|
|
}
|
|
}
|
|
|
|
// were all topology information collected?
|
|
if foundFreq &&
|
|
len(processor) > 0 &&
|
|
len(coreID) > 0 &&
|
|
len(physicalPackageID) > 0 {
|
|
|
|
globalID := physicalPackageID + ":" + coreID
|
|
|
|
// store collected topology information
|
|
m.topology = append(m.topology,
|
|
CPUFreqCpuInfoCollectorTopology{
|
|
isHT: coreSeenBefore[globalID],
|
|
tagSet: map[string]string{
|
|
"type": "hwthread",
|
|
"type-id": processor,
|
|
"package_id": physicalPackageID,
|
|
},
|
|
},
|
|
)
|
|
|
|
// mark core as seen before
|
|
coreSeenBefore[globalID] = true
|
|
|
|
// reset topology information
|
|
foundFreq = false
|
|
processor = ""
|
|
coreID = ""
|
|
physicalPackageID = ""
|
|
}
|
|
}
|
|
|
|
// Check if at least one CPU with frequency information was detected
|
|
if len(m.topology) == 0 {
|
|
return fmt.Errorf("No CPU frequency info found in %s", cpuInfoFile)
|
|
}
|
|
|
|
m.init = true
|
|
return nil
|
|
}
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMetric) {
|
|
// Check if already initialized
|
|
if !m.init {
|
|
return
|
|
}
|
|
|
|
const cpuInfoFile = "/proc/cpuinfo"
|
|
file, err := os.Open(cpuInfoFile)
|
|
if err != nil {
|
|
cclog.ComponentError(
|
|
m.name,
|
|
fmt.Sprintf("Read(): Failed to open file '%s': %v", cpuInfoFile, err))
|
|
return
|
|
}
|
|
defer file.Close()
|
|
|
|
processorCounter := 0
|
|
now := time.Now()
|
|
scanner := bufio.NewScanner(file)
|
|
for scanner.Scan() {
|
|
lineSplit := strings.Split(scanner.Text(), ":")
|
|
if len(lineSplit) == 2 {
|
|
key := strings.TrimSpace(lineSplit[0])
|
|
|
|
// frequency
|
|
if key == "cpu MHz" {
|
|
t := m.topology[processorCounter]
|
|
if !t.isHT {
|
|
value, err := strconv.ParseFloat(strings.TrimSpace(lineSplit[1]), 64)
|
|
if err != nil {
|
|
cclog.ComponentError(
|
|
m.name,
|
|
fmt.Sprintf("Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err))
|
|
return
|
|
}
|
|
if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
processorCounter++
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
func (m *CPUFreqCpuInfoCollector) Close() {
|
|
m.init = false
|
|
}
|